Optimization-Driven Deep Learning for Gait Recognition: Benchmarking the Hippopotamus Optimization Algorithm Against Established Metaheuristics.

Gait recognition has emerged as a robust biometric approach for human identification in surveillance, healthcare, and forensic applications. However, the efficiency of deep-learning-based gait recognition largely depends on the optimization algorithm used for model training and hyperparameter tuning. While traditional gradient-based methods such as Stochastic Gradient Descent (SGD) and Adam are widely adopted, their convergence behavior often deteriorates in high-dimensional non-convex spaces. Recent studies employing metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) have demonstrated performance gains but remain constrained by local optima and unstable convergence dynamics.
This study benchmarks a newly introduced metaheuristic; the Hippopotamus Optimization Algorithm (HOA) against four well-established optimizers: Adam, SGD, PSO, and GA, as reported in previous deep learning optimization studies. The developed HOA-CNN-LSTM hybrid model integrates the HOA for global hyperparameter optimization and Adam for fine-tuned gradient updates. Experiments conducted on the TUM-GAID dataset show that HOA achieves 97.4% accuracy and 98.5% Genuine Acceptance Rate (GAR) with a reduced convergence time of 39s per epoch. These results surpass comparative benchmarks reported for Adam [10], SGD [11], PSO [12], and GA [13], confirming HOA’s superior balance between exploration and exploitation.
By situating HOA’s performance within a metaheuristic benchmarking framework, this work provides empirical evidence that HOA represents a promising optimization paradigm for next-generation spatiotemporal deep learning and biometric recognition applications.

Biometric Identification, CNN-LSTM, Gait recognition

1. M. Nixon, T. Tan, and R. Chellappa, Human Identification Based on Gait. New York, NY, USA: Springer, 2010. [Google Scholar] [Crossref]

2. S. Yu, D. Tan, and T. Tan, “A framework for evaluating the effect of view angle, clothing, and carrying condition on gait recognition,” Pattern Recognition, vol. 41, no. 3, pp. 973–987, 2008. [Google Scholar] [Crossref]

3. C. Chen, J. Liang, H. Zhao, H. Hu, and J. Tian, “Frame difference energy image for gait recognition with incomplete silhouettes,” Pattern Recognition Letters, vol. 30, no. 11, pp. 977–984, 2009. [Google Scholar] [Crossref]

4. J. Han and B. Bhanu, “Individual recognition using gait energy image,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 2, pp. 316–322, Feb. 2006. [Google Scholar] [Crossref]

5. R. Collins, R. Gross, and J. Shi, “Silhouette-based human identification from body shape and gait,” in Proc. IEEE Conf. Automatic Face and Gesture Recognition, 2002, pp. 366–371. [Google Scholar] [Crossref]

6. Y. Zhang, D. Huang, and L. Wang, “Learning temporal representations for video-based gait recognition,” IEEE Transactions on Image Processing, vol. 29, pp. 1626–1637, 2020. [Google Scholar] [Crossref]

7. F. Chao, L. Liu, Y. Zhong, and C. Hu, “Hybrid CNN-LSTM for gait recognition,” Neural Computing and Applications, vol. 34, pp. 7035–7048, 2022. [Google Scholar] [Crossref]

8. M. N. Atansuyi and A. A. Adetunji, “Hybrid deep learning models for gait recognition: A comparative analysis of CNN, CNN-LSTM, and HOA techniques,” ResearchGate Preprint, DOI:10.13140/RG.2.2.39415.5249, 2025. [Google Scholar] [Crossref]

9. M. N. Atansuyi, “Efficient gait recognition using a CNN-LSTM framework optimized with Hippopotamus Algorithm,” ResearchGate Preprint, DOI:10.13140/RG.2.2.39424.4781, 2025. [Google Scholar] [Crossref]

10. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd Int. Conf. Learning Representations (ICLR), 2015. [Google Scholar] [Crossref]

11. S. Ruder, “An overview of gradient descent optimization algorithms,” arXiv preprint, arXiv:1609.04747, 2016. [Google Scholar] [Crossref]

12. R. Eberhart and J. Kennedy, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks, vol. 4, 1995, pp. 1942–1948. [Google Scholar] [Crossref]

13. J. H. Holland, Adaptation in Natural and Artificial Systems. Ann Arbor, MI, USA: Univ. Michigan Press, 1975. [Google Scholar] [Crossref]

14. M. Mirjalili, “The ant lion optimizer,” Advances in Engineering Software, vol. 83, pp. 80–98, 2015. [Google Scholar] [Crossref]

15. J. H. Abualigah, A. Diabat, S. Mirjalili, M. A. Elaziz, and A. H. Gandomi, “The Hippopotamus Optimization Algorithm: A new nature-inspired metaheuristic optimizer,” Expert Systems with Applications, vol. 207, p. 117–132, 2022. [Google Scholar] [Crossref]

16. S. Yang and X. Xu, “Deep feature optimization using bio-inspired algorithms: A review,” Applied Soft Computing, vol. 132, p. 109–142, 2023. [Google Scholar] [Crossref]

17. A. Singh and D. Kaur, “Optimizing deep convolutional networks using metaheuristic algorithms,” IEEE Access, vol. 9, pp. 66778–66790, 2021. [Google Scholar] [Crossref]

18. N. Ibne and R. Farhan, “Gait recognition under clothing and view variations using hybrid models,” IEEE Access, vol. 11, pp. 47212–47225, 2023. [Google Scholar] [Crossref]

19. M. Mitchell, An Introduction to Genetic Algorithms. Cambridge, MA, USA: MIT Press, 1996. [Google Scholar] [Crossref]

20. A. Rahman, M. Hossain, and A. Sarker, “Comparative performance of metaheuristic optimizers for deep neural networks,” Information Sciences, vol. 619, pp. 96–112, 2023. [Google Scholar] [Crossref]

21. L. He, Z. Zhang, and X. Liu, “Cross-dataset gait recognition using deep transfer learning,” Pattern Recognition, vol. 125, p. 108–141, 2022. [Google Scholar] [Crossref]

22. M. S. Khan, T. Ahmad, and M. A. Malik, “A hybrid HOA–PSO algorithm for global optimization,” Knowledge-Based Systems, vol. 289, p. 110–125, 2024. [Google Scholar] [Crossref]

23. S. Shiraga et al., “GEINet: View-invariant gait recognition using convolutional neural networks,” in Proc. Int. Conf. Biometrics (ICB), 2018, pp. 1–8. [Google Scholar] [Crossref]

24. H. Chao, Y. He, J. Zhang, and J. Feng, “GaitSet: Regarding gait as a set for cross-view gait recognition,” AAAI Conf. Artificial Intelligence, vol. 33, pp. 8126–8133, 2019. [Google Scholar] [Crossref]

25. [H. Fan, Y. Luo, and J. Wan, “GaitPart: Temporal part-based model for gait recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2020, pp. 14225–14233. [Google Scholar] [Crossref]

26. Y. Zhang, D. Huang, and L. Wang, “Learning temporal representations for video-based gait recognition,” IEEE Transactions on Image Processing, vol. 29, pp. 1626–1637, 2021. [Google Scholar] [Crossref]

27. P. Gupta and R. Mehra, “PSO-CNN-LSTM hybrid model for gait recognition,” International Journal of Intelligent Systems, vol. 38, no. 2, pp. 2271–2288, 2023. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet